© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3395
    Prev
    Next
    INDEX
    Explanations

    terms related to dimensions and measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    874
    +0.12
    0.7%
    122
    +0.12
    0.6%
    1034
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.12
    0.02
    1363
    +0.12
    0.02
    122
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.75
     intersper
    -1.16
    ⓧ
    -0.97
    /**
    -0.94
    
    -0.94
     encomp
    -0.93
    /***
    -0.93
    <?
    -0.91
     quitted
    -0.87
     chanced
    -0.87
    POSITIVE LOGITS
     dimension
    1.28
     Dimension
    1.21
     dimensions
    1.18
    dimension
    1.18
    Dimension
    1.15
     Dimensions
    1.10
    dimensions
    1.07
     Dim
    1.06
     Dimen
    1.05
    Dim
    1.04
    Activations Density 0.219%

    No Known Activations